Backward Bayesian reasoning helps LLM agents resolve conflicting diagnoses

On the DDXPlus diagnostic benchmark, a reverse posterior provided a complementary anchor for selecting, weighting, or combining answers from multiple LLM agents.

PaperTop Universitycs.AIarXiv:2609.11709v1
Ken Chen · Wei Wang · Sachith Seneviratne · Hansani Weeratunge · Saman Halgamuge

The University of Melbourne · Sri Lanka Institute of Information Technology

Research Digest··2 min read
Chen et al. construct a reverse, label-free posterior from an explicit likelihood and compare it with agents’ conventional forward predictions. Across five LLM backbones, combining the two reasoning paths performed better than forward-only aggregation, particularly when agents disagreed.

What they did

The authors evaluated multi-agent decision-making on DDXPlus, a medical differential-diagnosis benchmark, using five LLM backbones. For each instance, they paired agents’ forward posteriors—predictions derived from evidence—with a reverse posterior constructed through Bayesian backward reasoning from an explicit likelihood.

They measured agreement between the two paths using Jensen–Shannon divergence, a symmetric measure of distributional difference. This signal supported three aggregation strategies: selecting the most consistent agent (MinJS), reweighting forward predictions (FwdJS), and fusing forward and reverse distributions in log space (LogLin).

Key findings

  • MinJS outperformed random agent selection across all five LLM backbones.
  • FwdJS generally improved on the strongest evaluated baseline by assigning more weight to agents whose forward predictions agreed with the reverse anchor.
  • LogLin achieved the best overall performance among the evaluated methods, with its largest gains on cases where agents produced conflicting answers.
  • Although the reverse posterior was less accurate on its own, it was a more useful aggregation anchor than forward-only alternatives. When labels were available, a lightweight two-stage calibration improved it further.

Why it matters

The results suggest that multi-agent systems can benefit from combining differently factorized estimates, rather than merely voting over agents that may share correlated reasoning errors. A reverse inference path can provide an independent consistency check without requiring labeled examples, offering a practical way to arbitrate disagreement.

Caveats

The evidence is limited to DDXPlus and five LLM backbones, so it is unclear whether the gains extend to open-ended tasks, other domains, or settings without a tractable explicit likelihood. The abstract does not report effect sizes, and the reverse posterior’s weaker standalone accuracy indicates that its value depends on aggregation rather than superior independent prediction.

§

Analysis

Most multi-agent aggregation methods diversify prompts, models, or reasoning traces while retaining the same evidence-to-answer direction. This work instead introduces diversity at the level of probabilistic factorization, using disagreement between forward and backward inference as a reliability signal.

A central open question is how to construct trustworthy reverse likelihoods in less structured domains. If that step can be generalized, cross-path consistency could complement voting and learned judges in broader agent systems.

newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.